Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases expressing approximation or comparison

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating minimum qualifications or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iard
    -0.86
    raltar
    -0.80
    igr
    -0.78
    uesday
    -0.72
    Lastly
    -0.71
    ursday
    -0.69
    Ãį
    -0.68
    Then
    -0.66
    iw
    -0.66
    owler
    -0.65
    POSITIVE LOGITS
     Marketable
    0.80
    Downloadha
    0.77
     pretended
    0.72
     pretend
    0.72
    phan
    0.69
     contemplate
    0.68
     deserve
    0.66
     pretending
    0.66
     prefer
    0.65
     ought
    0.64
    Act Density 0.083%

    No Known Activations